Biomass supply chain resilience: integrating demand and availability predictions into routing decisions using machine learning

• Published in: Smart science Vol. 11; no. 2; pp. 293 - 317
• Main Authors: Esmaeili, Foad, Mafakheri, Fereshteh, Nasiri, Fuzhan
• Format: Journal Article
• Language: English
• Published: Taylor & Francis 03.04.2023
• Subjects: Bioenergy; demand prediction; machine learning; resilience; routing; supply chains
• ISSN: 2308-0477; 2308-0477
• DOI: 10.1080/23080477.2023.2176749

Biomass sources have the potential to mitigate carbon emissions as a renewable source while reducing waste and residues. Seasonality and disruption risks are some of the disadvantages of biomass resources requiring that biomass supply chains be managed such that to withstand disruptions. There has been very limited research on integrating predictions for smart management on supply or demand sides of biomass supply chains. In this study, a number of predictive models are investigated for building energy demand and biomass stock availability subject to forecasts of weather conditions. On that basis, an allocation algorithm is proposed for optimal collection and logistics of biomass from land to depots. Accordingly, Google Maps API will be used to identify the best distribution routes for delivering biomass from depots to end-users. A case study with real (supply and demand) data is considered. The proposed integrated data-driven approach aims at improving the accuracy of biomass supply and demand predictions and coordinating these predictions to enhance the resiliency of bioenergy supply chain routing decisions.